INDEX

Explanations

keywords related to legal actions and reversals of decisions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "overturn" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ebus

-0.73

artney

-0.73

uld

-0.67

iatrics

-0.66

isma

-0.63

awar

-0.62

mpeg

-0.62

ickr

-0.61

imen

-0.61

ymph

-0.61

POSITIVE LOGITS

 overturned

0.89

 overturn

0.80

 verdict

0.73

 rulings

0.67

ragon

0.64

uled

0.63

claw

0.62

 proceedings

0.62

 unanimously

0.61

 Burger

0.61

Activations Density 0.016%

keywords related to legal actions and reversals of decisions

occurrences of the word "overturn" and its variations

No Comments

No Known Activations